FreeSpan: frequent pattern-projected sequential pattern mining
Proceedings of the sixth ACM SIGKDD international conference on Knowledge discovery and data mining
SPADE: an efficient algorithm for mining frequent sequences
Machine Learning
Mining Sequential Patterns: Generalizations and Performance Improvements
EDBT '96 Proceedings of the 5th International Conference on Extending Database Technology: Advances in Database Technology
ICDE '95 Proceedings of the Eleventh International Conference on Data Engineering
Sequential PAttern mining using a bitmap representation
Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Mining Sequential Patterns by Pattern-Growth: The PrefixSpan Approach
IEEE Transactions on Knowledge and Data Engineering
Using d-gap patterns for index compression
Proceedings of the 16th international conference on World Wide Web
Contiguous item sequential pattern mining using UpDown Tree
Intelligent Data Analysis
Generalization of pattern-growth methods for sequential pattern mining with gap constraints
MLDM'03 Proceedings of the 3rd international conference on Machine learning and data mining in pattern recognition
BISC: A bitmap itemset support counting approach for efficient frequent itemset mining
ACM Transactions on Knowledge Discovery from Data (TKDD)
Hi-index | 0.00 |
Contiguous Sequential Pattern (CSP) mining is an important problem with many applications. Using general sequential pattern mining algorithms for CSP mining may lead to poor performance due to the lack of consideration on the contiguous property of CSP. In this paper we present a two stage approach for CSP mining. We first detect frequent itemsets in a database, based on which we partition the CSPs into subsets and apply a special data structure, General UpDown Tree, to detect all the patterns in each subset. The General Updown Tree exploits the contiguous property of CSPs to achieve a compact representation of all the sequences that contain an item. Such compact representation enables us to apply a top down approach for CSP mining and eliminates unnecessary candidate evaluation. Experiment results show that our approach is more efficient compared to previous approaches in terms of both time and space.